[1] Castleman K R, 朱志刚, 林学闵, 等. 数字图像处理[M]. 北京: 电子工业出版社, 1998: 123-145.

Castleman K R, Zhu Z, Lin X, et al. Digital Image Processing[M]. Beijing: Publishing House of Electronics Industry, 1998: 123-145. (in Chinese)
[2] Goodfellow I J, Bulatov Y, Ibarz J, et al. Multi-digit number recognition from street view imagery using deep convolutional neural networks [J]. arXiv preprint arXiv, 2013, 1312: 6082.
[3] 薛珊, 张振, 吕琼莹, 等. 基于卷积神经网络的反无人机系统图像识别方法[J]. 红外与激光工程, 2020, 49(7): 20200154. doi:  10.3788/IRLA20200154

Xue S, Zhang Z, Lv Q Y, et al. Image recognition method of anti UAV system based on convolutional neural network [J]. Infrared and Laser Engineering, 2020, 49(7): 20200154. (in Chinese) doi:  10.3788/IRLA20200154
[4] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[5] 王中宇, 倪显扬, 尚振东. 利用卷积神经网络的自动驾驶场景语义分割[J]. 光学精密工程, 2019, 27(11): 2429-2438. doi:  10.3788/OPE.20192711.2429

Wang Z Z, Ni X Y, Sheng Z D. Autonomous driving semantic segmentation with convolution neural networks [J]. Optics and Precision Engineering, 2019, 27(11): 2429-2438. (in Chinese) doi:  10.3788/OPE.20192711.2429
[6] Chao D, Chen C L, He K, et al. Learning a deep convolutional network for image super-resolution[C]//ECCV, Springer International Publishing, 2014, 8692: 184-199.
[7] 郝建坤, 黄玮, 刘军, 等. 空间变化PSF非盲去卷积图像复原法综述[J]. 中国光学, 2016, 9(1): 41-50. doi:  10.3788/co.20160901.0041

Hao J K, Huang W, Liu J, et al. Review of non-blind deconvolution image restoration based on spatially-varying PSF [J]. Chinese Optics, 2016, 9(1): 41-50. (in Chinese) doi:  10.3788/co.20160901.0041
[8] 朱明, 杨航, 贺柏根, 等. 联合梯度预测与导引滤波的图像运动模糊复原[J]. 中国光学, 2013, 6(6): 850-855.

Zhu M, Yang H, He B G, et al. Image motion blurring restoration of joint gradient prediction and guided filter [J]. Chinese Optics, 2013, 6(6): 850-855. (in Chinese)
[9] 张旭, 于明鑫, 祝连庆, 等. 基于全光衍射深度神经网络的矿物拉曼光谱识别方法[J]. 红外与激光工程, 2020, 49(10): 20200221.

Zhang X, Yu M X, Zhu L Q, et al. Raman mineral recognition method based on all-optical diffraction deep neural network [J]. Infrared and Laser Engineering, 2020, 49(10): 20200221. (in Chinese)
[10] 郭玉彬, 邢培. 一种全光模糊智能信息处理系统设计[J]. 光学精密工程, 1998, 6(1): 23-30. doi:  10.3321/j.issn:1004-924X.1998.01.005

Guo Y B, Xing P. The design of an all optical signal processing system with fuzzy intelligence networks [J]. Optics and Precision Engineering, 1998, 6(1): 23-30. (in Chinese) doi:  10.3321/j.issn:1004-924X.1998.01.005
[11] Xu S, Wang J, Wang R, et al. High-accuracy optical convolution unit architecture for convolutional neural networks by cascaded acousto-optical modulator arrays [J]. Optics Express, 2019, 27(14): 19778-19787. doi:  10.1364/OE.27.019778
[12] Mario Miscuglio, Zibo Hu, Shurui Li, et al. Massively parallel amplitude-only Fourier neural network [J]. Optica, 2020, 7(12): 1812-1819. doi:  10.1364/OPTICA.408659
[13] Wu Q, Fei Y, Liu J, et al. High speed and reconfigurable optronic neural network with digital nonlinear activation [J]. Optik, 2021, 247: 168043. doi:  10.1016/j.ijleo.2021.168043
[14] Gu Z, Gao Y, Liu X. Optronic convolutional neural networks of multi-layers with different functions executed in optics for image classification [J]. Optics Express, 2021, 29(4): 5877-5889. doi:  10.1364/OE.415542
[15] Sadeghzadeh H, Koohi S, Paranj A F. Free-space optical neural network based on optical nonlinearity and pooling operations [J]. IEEE Access, 2021, 9: 146533-146549. doi:  10.1109/ACCESS.2021.3123230